摘要
提出了一种基于小波神经网络整定的PID控制方法。由于小波变换具有良好的时频局部特性,神经网络具有强大的非线性映射能力,自学习、自适应等优势,采用规范正交的小波函数作为神经网络的基函数构成小波神经网络,该网络兼有小波函数的紧支性、波动性以及神经网络的非线性映射能力,自学习、自适应能力等优点,渗碳炉控制实验结果表明,用该方法整定的PID控制系统收敛速度快,逼近精度高,鲁棒性好。
A new PID tuning method based on wavelet neural network is presented. It introduces normalized wavelet basis functions as the basis of neural network. Benefited from wavelet transform' being constrictive and fluctuant, it shows excellent temporalfrequency localization property, while it possesses such merits as ability of mapping nonlinear systems, selflearning, selfadaptation and so on, thus, this network converges quickly with high precision and good robustness. Results of the carburizing furnace control are satisfactory and proves the method to be feasible and effective.
出处
《控制工程》
CSCD
2003年第6期532-535,共4页
Control Engineering of China
